Multi-stream speech recognition: ready for prime time?
نویسندگان
چکیده
Multi-stream and multi-band methods can improve the accuracy of speech recognition systems without overly increasing the complexity. However, they cannot be applied blindly. In this paper, we review our experience applying multi-stream and multiband methods to the Broadcast News corpus. We found that multi-stream systems using different acoustic front-ends provide a significant improvement over single stream systems. However, despite the fact that they have been successful on smaller tasks, we have not yet been able to show any improvement using multiband methods. We report various insights gained from the experience in applying these methods in a large-vocabulary task.
منابع مشابه
Submitted to Eurospeech’99, Budapest MULTI-STREAM SPEECH RECOGNITION: READY FOR PRIME TIME?
Multi-stream and multi-band methods can improve the accuracy of speech recognition systems without overly increasing the complexity. However, they cannot be applied blindly. In this paper, we review our experience applying multi-stream and multiband methods to the Broadcast News corpus. We found that multi-stream systems using different acoustic front-ends provide a significant improvement over...
متن کاملMulti-tape finite-state transducer for asynchronous multi-stream pattern recognition with application to speech
In this thesis, we have focused on improving the acoustic modeling of speech recognition systems to increase the overall recognition performance. We formulate a novel multi-stream speech recognition framework using multi-tape finite-state transducers (FSTs). The multi-dimensional input labels of the multi-tape FST transitions specify the acoustic models to be used for the individual feature str...
متن کاملEnsemble Feature Selection for Multi-Stream Automatic Speech Recognition
Ensemble Feature Selection for Multi-Stream Automatic Speech Recognition
متن کاملUsing the Multi Stream Approach for Continuous Audio Visual Speech Recognition Experiments on the M Vts Database
The Multi Stream automatic speech recognition approach was investigated in this work as a framework for Au dio Visual data fusion and speech recognition This method presents many potential advantages for such a task It particularly allows for synchronous decoding of continuous speech while still allowing for some asynchrony of the visual and acoustic information streams First the Multi Stream f...
متن کاملEfficient manycore CHMM speech recognition for audiovisual and multistream data
Robustness of speech recognition can be significantly improved by multi-stream and especially by audiovisual speech recognition. This is of interest for example for human-machine interaction in noisy reverberant environments, and for transcription of or search in multimedia data. The most robust implementations of audiovisual speech recognition often utilize Coupled Hidden Markov Models (CHMMs)...
متن کامل